* add onnx support to roi_align and roi_pool
* add softnms ort support
* fix for lint
* format cpp code with clang-format:google
* add new empty line to the end of head files in onnxruntime
* update to pytorch1.7
* add test of softnms to onnxruntime
* fix for lint
* remote print in ops/info.py
* change import order, fix for flake8
* fix include
* add assert torch>=1.7.0
* [doc]: add document for onnxruntime custom operator
* update onnxruntime version to v1.5.1 for softnms
* remove doc menu
* Resolve lint for markdown
* resolve naming style in onnxruntime_op.md
* Use old cpp apis, optimize test_onnx.py
* Fixing strings in tests/test_ops/test_onnx.py
* code format with yapf
* fix soft_nms parrot
* add import in onnxruntime setup, avoid conflict
* fix doc and add assert
* change cpp guard
Co-authored-by: maningsheng <maningsheng@sensetime.com>
* Allow to replace nested tuple and list via options
* Add comments
* Fix single nested items
* Simplify the code
* Simplify the code
* Simplify the code
* Simplify the code
* Update docstring
* Update docstring
* Support quotation mark
* modify docstring
* add jit decorator
* add parrots_jit.py
* modify test_parrots_jit.py
* modify for lint
* fix isort
* skip test_parrots_jit.py when build without pytorch
* try ci
* rm log
* fix double quote
* modify for comments and use partial_shape instead of full_shape
* fix for lint
* small modify for parrots 0.9.0rc0
* def skip no elena directly
* add clamp without unittest
* add clamp-act with unit test
* fix name bug
* use logical and
* fix logical_and
* fix linting
* rename ClampLayer to Clamp
* rename ClampLayer to Clamp
Co-authored-by: nbei <631557085@qq.com>
* Update lr_updater.py
since epoch/iteration in runner starts with 0, we shouldn't leave the latter iteration to former (12th epoch for example, with first period equal to 12) period.
* Update lr_updater.py
* Update test_hooks.py
* add unittest for onnx convert
* build onnx and onnxruntime in CI
* skip onnx op unit test while using CUDA
* fix offset==0 case in NMS
* remove tmp file used in test
* delete tmp file before assert so that we can remove the tmp file anyway
* import_modules_from_strings when loading cfg from file
* add unittest to tell whether the feature is enabled as expected
* minor
* set an environment variable instead of writing a file
* use 'shutil' instead of 'os.system'
* add version check in wrappers
* fix assersion
* use digital version for version comparison
* fix unit tests
* reformat
* fall back to compare the first two version
* fix unittest
* fix unittest
* fix unit test
* clean unnecessary change
* Support to specify LR of DCN's conv_offset
* Resolve comments & add unit test
* Resolve formats
* Fix CI for DCN
* Mock DCN when cpu only
* Use mock for cpu testing
* Fix docstring and support ModulatedDCN
* set offset_lr_mult as dcn's arguments, link CU-49u01p
* fix lr bug
* fall back to set LR in constructor
* resolve comments
* Add build_runner
* Parametrize test_runner
* Add imports to runner __init__
* Refactor max_iters and max_epochs from run to init
* Add assertion error messages
* Add test_builder
* Make change retro-compatible
* Raise ValueError if max_epochs and max_iters
* Add test case for type defined using default_args
* Refactor build_from_cfg
* Update exception of missing type
* pre-commit
* Fix default_args is None
* pre-commit
* Bring back test
* Update exception raising
* add brightness and contrast augmentation
* remove unnecessary
* reformat
* relax the precision constrain for adjust_brightness aug
* fix percision assertion error in unit test
* remove toy
* rename alpha as factor
* use np.testing.assert_allclose in place of np.less_equal
* Mv wrappers into bricks and use wrappers in registry
* resolve import issues
* fix import issues
* set nn op forward to torch 1.6.1
* fix CI bug and add warning
* Fix CI by using patch mock
* mv warnings inside deprecated module's initialization
* add equalize augmentation in mmcv
* delete unnecessary
* reformat
* remove clip in implementing equalize, and add uint test with case step=0
* remove clip in implementing equalize, and add uint test with case step=0
* add comments for unit test
* rename function name as imequalize
* add Color augmentation
* reformat
* reformat
* reformat docstring
* reformat docstring
* add more unit test
* add more unit test
* add clip value and uint test for image with type float
* rename function name
* Support to split batched_nms when box number is too large
* mv data from gpu to cpu
* Set split_thr through nms_cfg
* clean code
* Update motivation in docstring
* fix typos
* add ema hook
* add ema hook resume
* add ema hook test
* fix typo
* fix according to comment
* delete logger
* fix according to comment
* fix unitest
* fix typo
* fix according to comment
* change to resume_from
* typo
* fix isort
* add pairwise function for 'gaussian' and 'concatenation' mode
* rename test function
* decrease the complexity of nonlocal unittest
* fix typo and make unittest more complete
* add unittest when zero_init is False
* minor fix
* pack theta and phi
Co-authored-by: Jiarui XU <xvjiarui0826@gmail.com>
* fix: remove all module wrapper when saving checkpoint
* refactor: move position of if
* docs: add docstring
* refactor: add _save_to_state_dict from official torch
* docs: modify docstring of _save_to_state_dict
* docs: modify docstring
* feat: add unittest
* feat: add DataParallel to unittest
* fix: a bug when model has batchnorm
* docs: update docstring
* update config with predefined variables
* rm redun
Signed-off-by: lixuanyi <lixuanyi@sensetime.com>
* add test for config
Signed-off-by: lixuanyi <lixuanyi@sensetime.com>
* support all types
Signed-off-by: lixuanyi <lixuanyi@sensetime.com>
* newline at the end
Signed-off-by: lixuanyi <lixuanyi@sensetime.com>
* update
Signed-off-by: lixuanyi <lixuanyi@sensetime.com>
* extract code into a function and add docs
Signed-off-by: lixuanyi <lixuanyi@sensetime.com>
* fix and add tests
Signed-off-by: lixuanyi <lixuanyi@sensetime.com>
* add unit tests and fix
* fix
* fix minor
* fix test
* migrate op
* migrate unittest
* update build no torch
* add back use_torch_vision for roi align
* fix type and unit test
* ignore test logging when no torch
* fix no torch ci test
* skip test registry
* remove coverage report when no torch
* fix mac ci order
* install latest pillow when no torch
* mv convws to brisk
* update actiion
* remove 1.3 cuda
* reorder
* add no torch
* fixed version
* make py3.8 on pt1.5
* make py3.8 on pt1.5
* remove torch 1.3
* disable py3.8
* pip
* merge master with cuda compile fix
* add cpu roi align
* fixed test
* fixed no torch
* add CUDA_ARGS
* use one line
* gencode=61
* seperate jobs
* update lint
* use parametrize test
* formart and rename
* unit test for all
* add ext ops, support parrots
* fix lint
* fix lint
* update op from mmdetection
* support non-pytorch env
* fix import bug
* test not import mmcv.op
* rename mmcv.op to mmcv.ops
* fix compile warning
* 1. fix syncbn warning in pytorch 1.5
2. support only cpu compile
3. add point_sample from mmdet
* fix text bug
* update docstrings
* fix line endings
* minor updates
* remove non_local from ops
* bug fix for nonlocal2d
* rename ops_ext to _ext and _ext to _flow_warp_ext
* update the doc
* try clang-format github action
* fix github action
* add ops to api.rst
* fix cpp format
* fix clang format issues
* remove .clang-format
Co-authored-by: Kai Chen <chenkaidev@gmail.com>
* Add utils to calculate model complexity info
* remove _InstanceNorm in unittest
* add docstring and increase unittest coverage
* fix deconv_flops_counter_hook to accept different data shape
* test when model is not a common instance
* put flops_counter.py and weight_init.py into mmcv/cnn/utils folder
* fix import name
* reformat some docstrings
* update the scripts with latest one and remove redundant codes
* directly represent a model without string and eval()
* reformat code
* feat: support for os.environ port for slurm training
* fix: port data type
* feat: add flawed unittest
* feat: add flawed unittest
* docs: add comments
* fix: unittest
* fix: unittest
* add non_local module
* rewrite non local module comments
* perfect docstring and adjust init function
* not to init norm layer
* Correct initialize when there is a norm
* set normal method for both embedded_gaussian and dot_product
* feat: add custom_group to DefaultOptimConstrutor
* refactor: move custom_groups validate to _validate_cfg
* docs: add doc to explain custom_groups
* feat: add unittest for non_exist_key
* refactor: one param per group
* fix: small fix
* fix: name
* docs: docstring
* refactor: change to mult for only lr and wd custom
* docs: docstring
* docs: more explaination
* feat: sort custom key
* docs: add docstring
* refactor: use reverse arg of sorted
* docs: fix comment
* docs: fix comment
* refactor: small modi
* refactor: small modi
* refactor: small modi
* feat: add CosineRestartLrUpdaterHook
* style: rename period to periods
* fix: bug in period 0
* feat: rename eta_min to min_lr and add min_lr_ratio
* docs: fix docstring of restart lr updater
* refactor: use annealing_cos
* docs: add docstring to annealing_cos
* feat: cosine restart lr update hook
* refactor: modify code order for unittest
* add a BaseRunner and rename Runner to EpochBasedRunner
* fix the train/val step
* bug fix
* update unit tests
* fix unit tests
* raise an error if both batch_processor and train_step are set
* add a unit test
* Support path as a key in dict of config
* reformat test case
* update pre-commit version and fix format
* fix bug
* clean code
* reformat
* fix missing parts
* add building bricks of cnn
* add unit tests
* use registry for building bricks
* minor updates
* add scale layer
* add test for scale
* add doc string
Co-authored-by: Jiarui XU <xvjiarui0826@gmail.com>
* track progress of iter&enum
* restore
* add momentum scheduler
* fix small bug
* cyclic scheduler"
* fix bug
* fix second phase's bug
* reformat
* feature (cosine lr): use relative ratio for more flexible scheduler
* Fix (runner): fix bugs in runner
* Refactor (hook): refactor cosing/cyclic LR/momentum hook with unittest
* Clean unnecessary files and reformat
* Fix memory key error when GPU is not avaliable
* Resolve comments
* Do not print momentum in text log
* Change hook register order
* Refactor max_iter
* Fix max_iter bugs in runner
* Enforce target_ratio to be either tuple or float
* add base for config
* fixed format
* rm terminal width
* support multiple & recursive base
* add test case
* fix format
* add test construct
* minor fix
* add more test, rewrite merge from opt
* avoid depulicate keys
* delete imported config as module
* rename merge_from_dict
BigBigDream
Wenwei Zhang
q.yao
LXXXXR
Rui Xu
Wang Xinjiang
WRH
lml131
Kai Chen
BigBigDream
Jerry Jiarui XU
yamengxi
dreamerlin
Kuro Latency
David de la Iglesia Castro
robin Han
GT9505
David de la Iglesia Castro
Qiaofei Li
Xiaojie Li
Kevin
Cao Yuhang
Yuanhao Zhu
Jintao Lin
shilong
Jiamin
Yawei Li
Joanna
louzana
zhuyuanhao
lizz
Xintao
Jiangmiao Pang